© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11965
    Prev
    Next
    INDEX
    Explanations

    Java annotations and serialized names in class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "private" in Java/C++ code

    np_acts-logits-general · gemini-2.0-flash

    private keyword in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.51
    어
    -0.49
    δό
    -0.48
    lah
    -0.48
     "
    -0.47
    โ
    -0.45
    닝
    -0.44
     التن
    -0.44
    echo
    -0.44
     overall
    -0.44
    POSITIVE LOGITS
    private
    2.25
     private
    1.99
     PRIVATE
    1.52
     Private
    1.52
     privately
    1.36
    Private
    1.35
     prywat
    1.35
     privata
    1.33
     privat
    1.32
     privé
    1.31
    Activations Density 0.039%

    No Known Activations